Heart rate estimation by leveraging static and dynamic region weights
Liu, Lili; Xia, Zhaoqiang; Zhang, Xiaobiao; Peng, Jinye; Feng, Xiaoyi; Zhao, Guoying (2023-08-29)
SPIE
29.08.2023
Lili Liu, Zhaoqiang Xia, Xiaobiao Zhang, Jinye Peng, Xiaoyi Feng, and Guoying Zhao "Heart rate estimation by leveraging static and dynamic region weights," Journal of Electronic Imaging 32(4), 043037 (29 August 2023). https://doi.org/10.1117/1.JEI.32.4.043037
https://rightsstatements.org/vocab/InC/1.0/
© 2023 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202404222867
https://urn.fi/URN:NBN:fi:oulu-202404222867
Tiivistelmä
Abstract
As the demand for long-term health evaluation grows, researchers show increased interest in remote photoplethysmography studies. However, conventional methods are vulnerable to noise interference caused by non-rigid facial movements (facial expression, talking, etc.). Consequently, avoiding these interferences and improving the remote photoplethysmography (rPPG) signal quality become important tasks during heart rate (HR) estimation. We propose an approach that extracts high-quality rPPG signals from various subregions of the face by fusing static and dynamic weights and then employs the convolutional neural network to estimate HR value by converting the 1D rPPG signal into 2D time-frequency analysis maps. Specifically, chrominance features from various regions of interest are used to generate the raw subregion rPPG signal set that is further utilized to estimate the static weights of different regions through a clustering method. Additionally, a measurement method called enclosed area distance is proposed to perform static weights estimation. The dynamic weights of different regions are calculated using the 3D-gradient descriptor to eliminate motion interference, which evaluates the inactivation degree under regional movement situations. The final rPPG signal is reconstructed by combining the rPPG signals from the different subregions using the static and dynamic weights. The experiments are conducted on two widely used public datasets, i.e., MAHNOB-HCI and PURE. The results demonstrate that the proposed method achieves 3.12 MAE and 3.78 SD on MAHNOB-HCI and the best r on the PURE, which significantly outperforms state-of-the-art methods.
As the demand for long-term health evaluation grows, researchers show increased interest in remote photoplethysmography studies. However, conventional methods are vulnerable to noise interference caused by non-rigid facial movements (facial expression, talking, etc.). Consequently, avoiding these interferences and improving the remote photoplethysmography (rPPG) signal quality become important tasks during heart rate (HR) estimation. We propose an approach that extracts high-quality rPPG signals from various subregions of the face by fusing static and dynamic weights and then employs the convolutional neural network to estimate HR value by converting the 1D rPPG signal into 2D time-frequency analysis maps. Specifically, chrominance features from various regions of interest are used to generate the raw subregion rPPG signal set that is further utilized to estimate the static weights of different regions through a clustering method. Additionally, a measurement method called enclosed area distance is proposed to perform static weights estimation. The dynamic weights of different regions are calculated using the 3D-gradient descriptor to eliminate motion interference, which evaluates the inactivation degree under regional movement situations. The final rPPG signal is reconstructed by combining the rPPG signals from the different subregions using the static and dynamic weights. The experiments are conducted on two widely used public datasets, i.e., MAHNOB-HCI and PURE. The results demonstrate that the proposed method achieves 3.12 MAE and 3.78 SD on MAHNOB-HCI and the best r on the PURE, which significantly outperforms state-of-the-art methods.
Kokoelmat
- Avoin saatavuus [34164]